近年來，随著國內經濟邁向國際化及自由化，市場上操作工具也日漸多元化。在眾多投資工具中，『股票』對大多數人而言並不陌生，也是近幾年來最熱門的投資工具。
　　一般社會大眾在進行投資的時候，只會針對單一種股票進行投資，這種投資方法的風險相當大，往往會因為這一間公司或是企業小小的經營不順導致破產而造成投資者的損失，因此，如何做正確的投資是相當重要的。為了判斷某一家公司的股票是值得投資的，本研究利用分類股價指數作為控制組，選出各產業分類間較為優良的公司。另一方面，利用加權股價指數作為控制組，分類股價指數作為實驗組，目的在找出目前優於整個市場的產業有哪些，用來建議投資者，在做投資時，要以哪一種產業投資為主。本文利用夏普比值來篩選投資報酬率優於無風險利率的股票公司的以及利用一階段抽樣法改善母體變異數不相等的問題，同時利用多重比較方法來選取優於控制組的個股，然後再進一步建立最後股票投資組合以便分散風險。

　In recent years in Taiwan the financial market is on the move towards internationalization and liberalization. Among numerous investment vehicles, stock investment becomes increasingly important and is one of the most popular ones by small investors nowadays.
　Generally speaking, people can suffer heavy loss as they invest only in one stock if the stock company is operated poorly and possibly goes bankruptcy. Therefore, how to make a correct decision on stock selection becomes very important. In order to determine which company is worth investing, I use a Classified Stock Index as a control and then pick up those superior companies to the control and this similar work is carried through all categories of industries. Furthermore, I make use of Taiwan Weighed Stock Index as a control to find out which industries are superior to the entire stock market. According to selection methods discussed in this thesis, I have provided suggestions for investors on how to choose industries for investing. In addition, in this study, Sharpe ratio and one-stage multiple comparison method are used to choose those better stocks and then to construct a portfolio or combination of stocks to reduce investment risk.

1.Chen, Hubert J. and Chen, Shun-Yi (1999). A Range Test for the Equivalency of Means Under Unequal Variances, Technometrics, 41, 250-260.
2.Chen, H. J. and Lam, K. (1989). Single-stage interval estimation of the largest normal mean under heteroscedasticity eteroscedasticity. Communications in Statistics - Theory and Methods, 18(10), 3703-3718.
3.Chen, H. J. and Tsai P. J. (1980). Optimal confidence interval for the largest mean in repeated measurements design. Biometrika, 67, 119-126.
4.Dantzig, G. B. (1940). On the non-existence of tests of “student’s t” hypothesis having power functions independent of . Annals of Mathematical Statistics, 11, 186-192.
5.Dudewicz, E. J. and Dalal, S.R. (1975). Allocation of observations in ranking and selection with unequal variances. Sankhya ser. B, 37, 28-78.
6.Dunnett, C. W. (1955). A multiple comparison procedure for comparing several treatments with a control. Journal of American Statistical Association, 50, 1096-1121.
7.Dunnett, C. W. (1964). New tables for multiple comparisons with a control. Bio- metrics, 20, 482-491.
8.Gupta, S. S. (1956). On a decision rule for a problem in ranking means. Mimeograph Series N0. 150, Institute of Statistics, University of North Carolina, Chapel Hill, N. C.
9.Hsu, J. C. (1996). Multiple comparisons theory and methods. Chapman & Hall.
10.Johnson and Kotz (1972). Multivariate t-distributions. Distribution in statistics - Continuous multivariate Distribitions, Wiley. 37,132-157.
11.Ruppert, David. (2004). Statistics and finance - an introduction. Springer.
12.Searle, S. R. (1971). Linear models. Wiley. 43-53.
13.Slepian, D. (1962). The One-Sided Barrier Proglem for Gaussian Noise, Bell System Technology Journal, 41, 463-501.
14.Stein, C. (1945). A two-sample test for a linear hypothesis whose power is independent of the variance. Annals of Mathematical Statistics, 16, 243-258.
15.Wen, M. J. and Chen, H. J. (1994). Single-stage multiple comparison procedures under heteroscedasticity. American Journal of Mathematical and Management Sciences, 14(1,2), 1-48.
16.王義田 (2003)，股市操盤聖經。生智出版社。
17.韋端、張堯庭和謝邦昌 (2003)， 統計金融學。台灣知識庫。
18.謝劍平 (2004)，現代投資學。智勝出版社。
19.股票投資好學版 (1999)，金錢文化。